The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and evaluation data. It does not contain any executable code, scripts, or command-line instructions.
[SAFE]: No network operations, remote code execution, or external package installations are present in the instructions or reference materials.
[SAFE]: The skill does not access sensitive system paths, credentials, or environment variables.
[SAFE]: There are no prompt injection patterns, obfuscated contents, or persistence mechanisms detected within the skill files.
[SAFE]: The skill demonstrates proactive security awareness by warning the user about 'maintenance / security debt' and the fact that tools taking user input can become attack surfaces.
[SAFE]: While the skill instructions suggest reading local context files (e.g., '.agents/product-marketing.md'), it lacks any exploitable capabilities such as file writing, network calls, or subprocess execution that would represent an indirect prompt injection risk.

free-tools